INDEX

Explanations

mathematical expressions and notations, particularly those involving variables and equations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MessageTagHelper

-0.68

 незавершена

-0.65

CloseOperation

-0.60

يكب

-0.59

 AssemblyCompany

-0.59

 وتسجيلات

-0.59

 arşivlendi

-0.57

BeginContext

-0.56

TagMode

-0.56

multicolumn

-0.54

POSITIVE LOGITS

 subscript

0.75

 subs

0.63

Sklici

0.58

 denotes

0.57

 suffix

0.56

breviations

0.56

Atsauces

0.56

 notation

0.55

kilde

0.55

 notations

0.52

Activations Density 0.731%

mathematical expressions and notations, particularly those involving variables and equations

No Comments

No Known Activations